搜索资源列表
traditionalsp
- 语音信号的频域处理,语音虽然是一个时变、非平稳的随机过程。但在短时间内可近似看作是平稳的。因此如果能从带噪语音的短时谱中估计出“纯净”语音的短时谱,即可达到语音增强的目的。由于噪声也是随机过程,因此这种估计只能建立在统计模型基础上。利用人耳感知对语音频谱分量的相位不敏感的特性,这类语音增强算法主要针对短时谱的幅度估计。 -voice signals in the frequency domain processing, voice is a time-varying, nonstationa
planevoice1
- 航空噪声背景下的语音端点检测和语音增强算法,在信噪比很低的强航空噪声背景下,效果特别好-aviation noise background voice endpoint detection and voice enhancement algorithms, and very low signal to noise ratio in the strong aviation background noise, particularly effective
xiaobobianhuan
- 小波变换matlab程序 ,用于语音增强,已经通过测式,效果不凑-wavelet transform Matlab procedures for speech enhancement, he has passed the test-and the results do not follow
DTALK
- 结合回声消除和语音增强方法的double talk算法,能在噪声环境下定出语音的端点-light echo cancellation and voice enhancement method of double talk algorithm can be noisy environment set voice endpoint
wenier ehansment
- 利用韦纳滤波器进行语音增强,加入guassian噪声,然后在添加了噪声的语音后,使用weiner滤波器进行滤波。(speech enhancement using weiner filter, in this a speech is added with a guassian noise then after adding the noise the noise speech if filtered using weiner filter)
noise_estimation
- 压缩包内程序主要实现IMCRA算法,用于语音增强。(Compressed package program main realization IMCRA algorithm for speech enhancement.)
单麦克风
- 运用单麦克风实现语音增强,其中包括子程序,计算出了信噪比以及波形(Speech enhancement is realized by single microphone, including subroutine, and the SNR and waveform are calculated.)
10.5 FixedBeam.m
- 多通道语音增强办法----固定波束法 固定波束形成器的含义是其波束形成器的权值固定不变,与麦克风阵列的接收信号无关(Multi - channel speech enhancement method - fixed beam method)
Desktop
- 给纯净语音加上噪声,可以用在语音增强方面的实验(Add noise to pure voice)
语音去噪
- 这是关于维纳滤波去噪的算法,用于语音增强,对于学习语音技术有很大帮助
fixedbeam
- 经典麦克风语音增强算法,当阵元数目越多,语音增强效果越好(Classical microphone speech enhancement algorithm, the more the number of elements, the better the speech enhancement effect)
谱减法BOLL
- 对基于残留噪声去除的谱减法的编程,实现了高去噪水平(The program of spectral subtraction based on residual noise removal has achieved high denoising level.)
sednn-master.tar
- 利用DNN来进行语音增强,先补充数据训练模型,然后进行去噪处理。(speech enhancement:Using DNN to enhance speech, data training model is first supplemented and then denoised.)
Generalised-Side-Lobe-Canceller-master
- 麦克风阵列处理-GSC(Generalized Sidelobe Canceller,广义旁瓣相消器)(GSC Generalized Sidelobe Canceller audio)
Speech-enhancement-dsp-master
- 几种传统的语音增强方法,适合初学者,了解语音增强的处理。(Several traditional speech enhancement methods are suitable for beginners to understand the processing of speech enhancement.)
SpeechEnhancement
- 有完整的代码注释,三种方法都可以实现,并有demo音频。(There are complete code annotations, all three methods can be implemented, and demo audio.)
BeamF
- 麦克风阵列语音增强处理,采用固定波束形成算法实现(Microphone array speech enhancement processing is realized by fixed beamforming algorithm.)
yasuo
- 麦克风阵列增强入门资料,麦克风阵列语音增强算法研究(Introduction to Microphone Array Enhancement and Research on Microphone Array Speech Enhancement Algorithms)
实验
- 此代码为传统语音增强算法的对比,包括谱减法、维纳滤波,自适应滤波,适合语音信号初学者使用。(This code is a comparison of traditional speech enhancement algorithms, including spectral subtraction, Wiener filtering, adaptive filtering, suitable for beginners to use voice signals.)
IMCRA111
- IMCRA(Improved?Minima Controlled Recursive Averaging,IMCRA),它们虽然保证了噪声谱估计的准确性,但在追踪带噪语音平滑功率谱最小值时采用了固定时间窗,因此,在噪声突变的情况下,估计的噪声谱存在很长的延时。(IMCRA, Although they ensure the accuracy of noise spectrum estimation, they use a fixed time window to track the minimu